{"id":"W2047499569","doi":"10.1109/tpami.2011.228","title":"Discriminative Latent Models for Recognizing Contextual Group Activities","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":312,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Canadian Institutes of Health Research","keywords":"Discriminative model; Computer science; Inference; Latent variable; Artificial intelligence; Feature (linguistics); Context (archaeology); Representation (politics); Action (physics); Focus (optics); Machine learning","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001856802,0.0001987497,0.0002667994,0.0004437387,0.0002808051,0.0001088202,0.0002471005,0.00005707191,0.0001266758],"category_scores_gemma":[0.000002793949,0.0001731066,0.0002738193,0.0003618429,0.00006144955,0.0007034401,0.00000464031,0.0001699512,0.0000116359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002885334,"about_ca_system_score_gemma":0.000009514222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005699478,"about_ca_topic_score_gemma":0.001062424,"domain_scores_codex":[0.9987903,0.00006515754,0.000299223,0.0004680222,0.0001576269,0.0002196792],"domain_scores_gemma":[0.9992892,0.000175882,0.0001126756,0.0002461023,0.000078852,0.00009733316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002412982,0.0002442923,0.0000317895,0.00001562262,0.0004749536,0.000003222716,0.002946261,0.001038466,0.0001651306,0.001015218,0.000005139364,0.9940358],"study_design_scores_gemma":[0.0002938258,0.0005750856,0.0003674215,0.00005806525,0.0008722274,0.00001132436,0.0008076518,0.7038067,0.2801678,0.0124278,0.00004068614,0.0005713966],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00519122,0.00003586228,0.9938212,0.00007288292,0.0002161137,0.0001958068,0.00006796652,0.00008975364,0.0003091705],"genre_scores_gemma":[0.9951034,0.0001968495,0.004068508,0.0002916691,0.00001583991,0.00009317158,0.000009003139,0.0000108709,0.0002106661],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9934644,"threshold_uncertainty_score":0.7059081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08053272526626618,"score_gpt":0.2779632148624597,"score_spread":0.1974304895961936,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}